--- title: Gemini 4 Argon matches GPT-6 Astra and hallucinates far... description: Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's GPT-6 Astra and trailing Claude Opus 5.5 (58). Argon... canonical: https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Gemini 4 Argon matches GPT-6 Astra and hallucinates far less in early tests | daily.dev og:description: Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's GPT-6 Astra and trailing Claude Opus 5.5 (58). Argon... og:url: https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2 og:image: https://api.daily.dev/og/posts/PxnXyclp2.png og:image:alt: Gemini 4 Argon matches GPT-6 Astra and hallucinates far less in early tests og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 4 Argon matches GPT-6 Astra and hallucinates far less in early tests **[The Next Web](https://daily.dev/sources/tnw)** · 3 min read · 0 upvotes · 0 comments ## Summary Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's GPT-6 Astra and trailing Claude Opus 5.5 (58). Argon hallucinates far less (15% vs 51-54% for GPT-6 models) but also answers fewer questions correctly. It costs 60% of GPT-6 Astra per task at launch discount pricing, though it uses more than double the output tokens. Argon leads Arena's Text Arena and the Vals Index, but Bloomberg reports internal Google skepticism about its coding and front-end design abilities, with some staff suspecting benchmark-chasing over genuine product quality. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Gemini 4 Argon's hallucination rate compare to GPT-6 Astra and GPT-6.1 Sol? Gemini 4 Argon has a 15% hallucination rate on the AA-Omniscience test, the lowest among models scoring 45 or higher on the Artificial Analysis Intelligence Index. GPT-6 Astra hallucinates 51% of the time and GPT-6.1 Sol 54%. Argon more often admits uncertainty instead of guessing, but it also answers correctly less often overall, at 50% versus 63% for GPT-6 Astra. _Developers choosing between models for factual accuracy can track benchmark comparisons like this on daily.dev._ ### How does the cost per task of Gemini 4 Argon compare to GPT-6 Astra and GPT-6.1 Sol? Each Artificial Analysis Intelligence Index task costs $1.99 with Gemini 4 Argon at its launch discount, about 60% of GPT-6 Astra's $3.26 per task. The saving comes from lower token prices rather than fewer tokens used, since Argon generates roughly 62,000 output tokens per task versus 27,000 for GPT-6 Astra. At standard pricing ($4 input/$20 output per million tokens), each task would cost $3.98, and Argon still costs 2.7 times as much per task as GPT-6.1 Sol. _Teams budgeting API spend across model providers can follow pricing shifts like this on daily.dev._ ### How did Gemini 4 Argon perform on coding benchmarks compared to Claude models? On Terminal Bench 4, a coding test, Gemini 4 Argon scored 57%, trailing Claude Sonnet 5.5 (64%), Claude Opus 5.5 (60%), and GPT-6 Astra (59%). Some Google staff reportedly consider Argon's coding abilities uneven and view it as weaker at front-end design, with two people suggesting the model shows signs of benchmark-chasing rather than genuine product quality. _Developers picking a coding model can weigh benchmark gaps like these on daily.dev before switching._ ## Similar posts on daily.dev - [Gemini 4 Argon: Google’s New AI Is Built to Think and Work for Much Longer](https://daily.dev/posts/gemini-4-argon-google-s-new-ai-is-built-to-think-and-work-for-much-longer-ibbgfhpdj) · Medium · 0 upvotes · 0 comments - [OpenAI launches GPT-6 Astra and says welcome to the “AGI era”](https://daily.dev/posts/openai-launches-gpt-6-astra-and-says-welcome-to-the-agi-era--e6ipmuzta) · The New Stack · 6 upvotes · 0 comments - [GPT-6 Astra Benchmarks: 99.9% or 62.7%? The Full ARC-AGI-3 Story](https://daily.dev/posts/gpt-6-astra-benchmarks-99-9-or-62-7-the-full-arc-agi-3-story-1dabqghdx) · Medium · 1 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#claude](https://daily.dev/tags/claude), [#google-gemini](https://daily.dev/tags/google-gemini), [#gpt](https://daily.dev/tags/gpt) [View this post on daily.dev](https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Gemini 4 Argon matches GPT-6 Astra and hallucinates far less in early tests","url":"https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2"},"datePublished":"2026-10-02T11:11:45.450Z","dateModified":"2026-10-02T11:12:36.183Z","description":"Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's GPT-6 Astra and trailing Claude Opus 5.5 (58). Argon...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/86aad9f33e7eb4f698ea12bfbe9ec599?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/86aad9f33e7eb4f698ea12bfbe9ec599?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,claude,google-gemini,gpt","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"Gemini 4 Argon matches GPT-6 Astra and hallucinates far less in early tests"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/gemini-4-argon-matches-gpt-6-astra-and-hallucinates-far-less-in-early-tests-pxnxyclp2#faq","mainEntity":[{"@type":"Question","name":"How does Gemini 4 Argon's hallucination rate compare to GPT-6 Astra and GPT-6.1 Sol?","acceptedAnswer":{"@type":"Answer","text":"Gemini 4 Argon has a 15% hallucination rate on the AA-Omniscience test, the lowest among models scoring 45 or higher on the Artificial Analysis Intelligence Index. GPT-6 Astra hallucinates 51% of the time and GPT-6.1 Sol 54%. Argon more often admits uncertainty instead of guessing, but it also answers correctly less often overall, at 50% versus 63% for GPT-6 Astra. Developers choosing between models for factual accuracy can track benchmark comparisons like this on daily.dev."}},{"@type":"Question","name":"How does the cost per task of Gemini 4 Argon compare to GPT-6 Astra and GPT-6.1 Sol?","acceptedAnswer":{"@type":"Answer","text":"Each Artificial Analysis Intelligence Index task costs $1.99 with Gemini 4 Argon at its launch discount, about 60% of GPT-6 Astra's $3.26 per task. The saving comes from lower token prices rather than fewer tokens used, since Argon generates roughly 62,000 output tokens per task versus 27,000 for GPT-6 Astra. At standard pricing ($4 input/$20 output per million tokens), each task would cost $3.98, and Argon still costs 2.7 times as much per task as GPT-6.1 Sol. Teams budgeting API spend across model providers can follow pricing shifts like this on daily.dev."}},{"@type":"Question","name":"How did Gemini 4 Argon perform on coding benchmarks compared to Claude models?","acceptedAnswer":{"@type":"Answer","text":"On Terminal Bench 4, a coding test, Gemini 4 Argon scored 57%, trailing Claude Sonnet 5.5 (64%), Claude Opus 5.5 (60%), and GPT-6 Astra (59%). Some Google staff reportedly consider Argon's coding abilities uneven and view it as weaker at front-end design, with two people suggesting the model shows signs of benchmark-chasing rather than genuine product quality. Developers picking a coding model can weigh benchmark gaps like these on daily.dev before switching."}}]} ```